Triple
T8612960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Dupont Ice Arena |
E203958
|
entity |
| Predicate | supportsTeamType |
P33564
|
FINISHED |
| Object | youth hockey teams |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: youth hockey teams | Statement: [Fort Dupont Ice Arena, supportsTeamType, youth hockey teams]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsTeamType Context triple: [Fort Dupont Ice Arena, supportsTeamType, youth hockey teams]
-
A.
supportsTeam
Indicates that one entity provides backing, assistance, or endorsement to a particular team.
-
B.
supportsTeamFrom
Indicates that one entity actively backs, favors, or roots for a particular team.
-
C.
supportsTeamLevel
Indicates that one entity provides assistance, resources, or endorsement to a team as a whole rather than to individual members.
-
D.
supportsParticipantType
chosen
Indicates that an entity is compatible with, or designed to work with, a specified type or category of participant.
-
E.
supportsTeamInCity
Indicates that one entity provides backing or assistance to a sports team that is based in a particular city.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca832c23e4819095a9f3eea4a21828 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc46fdf21c81908ffc6363e98ab871 |
completed | March 31, 2026, 10:13 p.m. |
| PD | Predicate disambiguation | batch_69cc455437488190b7506f820daf6e32 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:25 p.m.